The Multi-Genre Broadcast (MGB) Challenge is an evaluation of speech recognition, speaker diarization, and lightly supervised alignment using TV recordings in English and Arabic.
The speech data is broad and multi-genre, spanning the whole range of TV output, and represents a challenging task for speech technology.
In 2015, the challenge used data from the British Broadcasting Corporation (BBC). It was an official challenge of the 2015 IEEE Automatic Speech Recognition and Understanding Workshop. In 2016, the Challenge will feature two new Arabic tracks based on TV data from Aljazeera. Unfortunately, due to ongoing licensing issues, we will not be able to re-run the English MGB Challenge in 2016, but we hope to run a second version in future years.
We hope that participation in the challenge will give: